ML Performance Tooling Engineer: Optimize Latency & Scale

Wayve Technologies Ltd.; Greater London; Hybrid; GBP 90,000 - 140,000; Full time

Job summary

Wayve seeks a Software Engineer, AI Performance Tooling, to design and build self-service tools that measure, monitor and predict AI performance across models, hardware targets and training runs.

You will collaborate with model, compiler, runtime, platform and hardware teams to translate profiling data into actionable recommendations, improving latency, memory usage and compute efficiency. The role is hybrid, with in-office collaboration and time for focused work.

Qualifications

• Hands-on performance engineering in complex systems and profiling.
• Owns a tool or service end-to-end—design, delivery and adoption.

Responsibilities

• Design and build reliable, self-service performance tools that scale across models and hardware targets.
• Shape how Wayve measures and predicts AI performance and set standards for others to follow.
• Model theoretical peak for a platform, compare with achieved performance, and identify bottlenecks.

Skills

Performance engineering

Python

Data analysis

Profiling

Latency optimization

Root-cause analysis

Communication

Prioritization

Tools

PyTorch

Job description

Wayve seeks a Software Engineer, AI Performance Tooling, to design and build self-service tools that measure, monitor and predict AI performance across models, hardware targets and training runs.

You will collaborate with model, compiler, runtime, platform and hardware teams to translate profiling data into actionable recommendations, improving latency, memory usage and compute efficiency. The role is hybrid, with in-office collaboration and time for focused work.